{"id":"W4399772732","doi":"10.2196/60280","title":"Peer Review of “Performance Drift in Machine Learning Models for Cardiac Surgery Risk Prediction: Retrospective Analysis”","year":2024,"lang":"en","type":"article","venue":"JMIRx Med","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Medicine; Computer science; Cardiology; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04781928,0.0008511985,0.001531989,0.007193983,0.002895094,0.005832436,0.002719565,0.00249313,0.05534982],"category_scores_gemma":[0.329505,0.0004936977,0.00126849,0.005555691,0.002054867,0.003969371,0.00369894,0.00271068,0.03168167],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00276976,"about_ca_system_score_gemma":0.01154175,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003753769,"about_ca_topic_score_gemma":0.005068989,"domain_scores_codex":[0.9538292,0.01439536,0.005026748,0.002809116,0.02291659,0.001022922],"domain_scores_gemma":[0.4534642,0.06398025,0.01749764,0.02122129,0.4370736,0.006763],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000148304,0.00003084953,0.00358706,0.001139681,0.0001199469,0.0001333363,0.0002221641,0.0001976349,0.0003912104,0.001103933,0.9179525,0.07497339],"study_design_scores_gemma":[0.00008471309,0.0001257938,0.009847328,0.002263684,0.0001503356,0.0003562088,0.000531613,0.002466563,0.001964627,0.00272305,0.9793829,0.0001032404],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"editorial","genre_gemma":"empirical","genre_scores_codex":[0.022299,0.0237966,0.04599252,0.3335139,0.4708696,0.003292658,0.02098691,0.005261432,0.07398731],"genre_scores_gemma":[0.3096607,0.04219649,0.04923736,0.07786962,0.220569,0.004035349,0.04823317,0.008816987,0.2393814],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9521807,"threshold_uncertainty_score":0.2528956,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03087608632671638,"score_gpt":0.3063412251667841,"score_spread":0.2754651388400677,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}